INDEX

Explanations

instances of phrases with the word "that" preceding a verb

oai_token-act-pair · gpt-3.5-turbo

the phrase "that" in various contexts, indicating references or conditions related to people or situations

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.8.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AND

-0.68

 Meaning

-0.66

 Usage

-0.63

onsequ

-0.63

ising

-0.61

 proof

-0.58

 apologies

-0.58

 semantics

-0.55

 Trop

-0.55

PLIC

-0.54

POSITIVE LOGITS

 owns

0.98

 specializes

0.85

 specialize

0.85

 participated

0.84

 invests

0.80

 violates

0.79

 grew

0.77

 inhabit

0.77

ate

0.76

 embodies

0.75

Activations Density 0.103%

instances of phrases with the word "that" preceding a verb

the phrase "that" in various contexts, indicating references or conditions related to people or situations

No Comments

No Known Activations